Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2768 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2339. Min Act: -0.0001

Data Index: 216010 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2006. Min Act: -0.0001

Data Index: 428384 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1446. Min Act: -0.0001

Data Index: 409526 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1556. Min Act: -0.0001

Data Index: 318234 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1425. Min Act: -0.0001

Data Index: 507405 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1260. Min Act: -0.0001

Data Index: 1267203 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1302. Min Act: -0.0001

Data Index: 496751 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1186. Min Act: -0.0001

Data Index: 646773 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1306. Min Act: -0.0001

Data Index: 920038 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1206. Min Act: -0.0001

Data Index: 592541 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1169. Min Act: -0.0001

Data Index: 149669 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1258. Min Act: -0.0001

Data Index: 112238 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1249. Min Act: -0.0001

Data Index: 605299 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1243. Min Act: -0.0001

Data Index: 234358 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1091. Min Act: -0.0001

Data Index: 934224 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1132. Min Act: -0.0001

Data Index: 339062 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1153. Min Act: -0.0001

Data Index: 1099070 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1157. Min Act: -0.0001

Data Index: 772533 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1158. Min Act: -0.0001

Data Index: 300437 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1305. Min Act: -0.0001

Data Index: 573343 (C4 (Web Text))

Max Activating Token Index: 343